A novel approach for holographic 3D content generation without depth map

TL;DR

This paper introduces a deep learning method to generate holographic 3D content using only RGB images, eliminating the need for depth maps and enabling hologram creation in data-scarce environments.

Contribution

A novel deep learning approach that synthesizes volumetric holograms solely from RGB images, bypassing the requirement for depth maps.

Findings

Generated holograms are more accurate than competing models.

The method works effectively with only RGB data.

It enables hologram synthesis in scenarios lacking depth information.

Abstract

In preparation for observing holographic 3D content, acquiring a set of RGB color and depth map images per scene is necessary to generate computer-generated holograms (CGHs) when using the fast Fourier transform (FFT) algorithm. However, in real-world situations, these paired formats of RGB color and depth map images are not always fully available. We propose a deep learning-based method to synthesize the volumetric digital holograms using only the given RGB image, so that we can overcome environments where RGB color and depth map images are partially provided. The proposed method uses only the input of RGB image to estimate its depth map and then generate its CGH sequentially. Through experiments, we demonstrate that the volumetric hologram generated through our proposed model is more accurate than that of competitive models, under the situation that only RGB color data can be provided.